The work item was adopted at an ITU-T Study Group 11 meeting held in Geneva from 14 to 22 July, following a proposal from SKT. ITU-T is the telecoms standardisation arm of the ITU, the UN’s specialised agency for information and communications technologies, and counts around 1,000 institutions, companies and research organisations from roughly 190 member countries among its participants.
The proposal addresses a compatibility problem in robotics AI training. Motion data used to train intelligent robots, including humanoids, is currently produced and exchanged differently across robot models and onboard software, limiting the scale and consistency of datasets available for AI development. SKT’s RDF framework sets out to define the key functions, interworking structure and data exchange methods needed to standardise this process.
Under the adopted work item, RDF is divided into five layers: Service, Robot Model/Data, Infrastructure, Device and Management. SKT said it plans to establish interworking specifications between these layers so that functions can be connected, replaced and expanded across different robots and platforms.
The move builds on SKT’s existing digital twin platform for manufacturing AI, which the operator is extending into a robot learning platform that generates task data for AI training. SKT said its accumulated digital twin, AI and data capabilities underpinned the successful adoption of the work item. The digital twin-based robot learning platform is due to launch in the second half of 2026.
“With the adoption of this new standardisation work item, SKT has established a foundation for leading international standards discussions, leveraging the digital twin and AI capabilities it has accumulated in the Physical AI field,” said Choi Dong-hee, head of AI Strategy Planning Office at SKT.
SKT said it intends to expand cooperation with domestic and international robotics and AI companies and research institutions on the back of the standardisation discussion, with the aim of supporting wider development of the robot data ecosystem.
RELATED STORIES
SK Telecom’s 15GW data centre project promises to make Korea an AI hub
SK Telecom boosts expansion of AI data centre initiative with global partnerships
Capacity Europe 2026
The 24th anniversary edition of Capacity Europe 2025 will bring together 3,500+ decision-makers from the global connectivity and digital infrastructure community.
